Category Archives: AI
Amazon Polly Hello World with Java & Spring Boot
Amazon Polly is one cool AWS service which can be used to achieve requirements such as creating business, security alerts via phone call. When integrated with communication providers such as Twilio, several value-added services could be created using Amazon Polly AWS service. In this post, you will learn about creating a sample Java app which uses Amazon Polly service for converting text to speech. You should be able to listen to the following text using the program given below: Hello World! How are you doing? This is Polly. I am happy to talk with you. The following are some of the aspects covered in this post: Create a Spring Boot app …
8 Machine Learning Javascript Frameworks to Explore
Javascript developers tend to look out for Javascript frameworks which can be used to train machine learning models based on different machine learning algorithms. The following are some of the machine learning algorithms using which models can be trained using different javascript frameworks listed in this article: Simple linear regression Multi-variate linrear regression Logistic regression Naive-bayesian K-nearest neighbour (KNN) K-means Support vector machine (SVM) Random forest Decision tree Feedforward neural network Deep learning network In this post, you will learn about different Javascsript framework for machine learning. They are some of the following: Deeplearn.js Propel ConvNetJS ML-JS KerasJS STDLib Limdu.js Brain.js DeepLearn.js Deeplearn.js is an open-source machine learning Javascript library …
Sentiment Analysis Examples using Google Cloud NLP API
Sentiment analysis of a text document such as speech, articles on websites etc is about assessing sentiments associated with the document as a function of overall emotions expressed in form of different words. Sentiment analysis is primarily used for tracking voice of customer (VOC) by analyzing customer reviews, survey responses, etc., in social media websites such as Facebook, Twitter etc. The VOC can be related to products in general, an event, movies etc. In this post, you will learn about how to use Google Cloud NLP API for performing sentiment analysis of a text document. Java code is used for programming the sentiment analysis. Google NLP API – Sentiment Analysis Metrics …
How to Create Java NLP Apps using Google NLP API
Natural language processing (NLP) is an AI-based technology which is used for creating apps related to speech recognition, natural-language understanding, and natural-language generation. Some of the applications related to NLP are content classification, sentiment analysis, syntactic analysis etc. In this post, you will learn about how to get set up with a development environment for creating NLP based apps using Google Cloud NLP APIs. Setup Eclipse-based Development Environment for Google NLP API The steps below would help you get setup with Eclipse IDE and Java-based development environment for developing apps using Google Cloud Natural Language API. Create Google Project: Create a project by logging into Google Cloud console. I created …
N-Gram Language Models Explained with Examples
Language models are models which assign probabilities to a sentence or a sequence of words or, probability of an upcoming word given previous set of words. Language models are used in fields such as speech recognition, spelling correction, machine translation etc. Language models are primarily of two kinds: N-Gram language models Grammar-based language models such as probabilistic context-free grammars (PCFGs) In this post, you will learn about some of the following: Introduction to Language Models N-Grams language models Introduction to Language Models Language models, as mentioned above, is used to determine the probability of occurrence of a sentence or a sequence of words. Language models are created based on following …
Quick Introduction to Smoothing Techniques for Language Models
Smoothing techniques in NLP are used to address scenarios related to determining probability / likelihood estimate of a sequence of words (say, a sentence) occuring together when one or more words individually (unigram) or N-grams such as bigram([latex]w_{i}[/latex]/[latex]w_{i-1}[/latex]) or trigram ([latex]w_{i}[/latex]/[latex]w_{i-1}w_{i-2}[/latex]) in the given set have never occured in the past. In this post, you will go through a quick introduction to various different smoothing techniques used in NLP in addition to related formulas and examples. The following is the list of some of the smoothing techniques: Laplace smoothing: Another name for Laplace smoothing technique is add one smoothing. Additive smoothing Good-turing smoothing Kneser-Ney smoothing Katz smoothing Church and Gale Smoothing …
Startups – Varo Money uses AI to Improve Customers Financial Health
Varo Money, a fintech startup, is using AI (machine learning) along with mobile banking to improve customers’ financial health. It recently raised $45 million from a private equity giant, Warburg Pincus and The Rise Fund, a global impact fund. The following are some of the features of Varo Money product which looks to have been created using machine learning algorithms/techniques. Predict cashflow projections for informed spending: This is one of the key features of Varo Money AI-powered product. A supervised learning problem which could be solved using multilinear regression analysis. The underlying machine learning model could take into account some of the following features to predict the cashflow in near …
Top 10 Startups Building Speech-to-text Conversion Solutions
This is a list of 10 startups which are using speech recognition technology (Speech-to-text Conversion) to solve different problems. Startup Name What they are doing Behavioral Signals Building emotion recognition and behavioral analytics technology; They are speech-to-text conversion with AI to create powerful predictions. SpeakSee Makes conversations visual and easy to hear for the deaf and hard-of-hearing; It may require integration with Cloud Speech API integration to get real time transcription. HelixAI Helps scientists, researchers, and lab technicians access information and reference data simply using their voice; Spitch Swiss-based provider of solutions in Automatic Speech Recognition (ASR), Voice Biometrics, Voice User Interfaces (VUI), and natural language voice data analytics. The …
How to Build Liv.ai like Speech-to-text Conversion Platform
This article explores the technology landscape which can be used to build similar platform / service offerings like Liv.ai. First and foremost, congratulations to Liv.ai team for leveraging existing cloud-based AI and speech recognition (Speech-to-text conversion) technologies to come up with a set of business offerings which leverages speech-to-text conversion technology to create great value for businesses. The founding team (IIT KGP Alumni – Subodh Kumar, Sanjeev Kumar and Kishore Mundra) nailed it! Doing right thing at right time at right place. Liv.ai enables developers to convert speech-to-text by using Powerful Neural Network Models with exceptional accuracy and minimal latency. At this point, the platform supports 9 languages including Hindi, English, Bengali, Gujarati, Telugu, Tamil, Marathi, …
CareNGrow powers Preventive Healthcare Platform with AI & Cloud-Computing
CareNGrow is building a preventive healthcare platform based on AI and cloud-computing technologies. One of the goals is creating and monitoring the physical, psychological, and behavioural health profile of children in schools. The following represents key workflow steps which is implemented while examining a kid / child: Data gathering Transfer data over internet to cloud Feed the data into the analytics platform Perform the data analysis (Predictive Analytics) Generate health reports This is a brainchild of a young doctor, Dr. Meghana Kambham. CareNGrow is already making waves in different startup competitions owing to the work they have been doing. In this relation, they have been announced as one of the UberExchange winners. Check …
Proscia uses AI-powered Digital Pathology for Cancer Screening
Proscia, a cloud-based digital pathology provider is on a mission to bring computer intelligence (using artificial intelligence (AI)) to pathology, fighting cancer by unlocking the data hidden in tissue. The following are some of the key aspects of cloud-based digital pathology technology of Proscia: Telepathology Data management Pathology Cloud Web application for managing/sharing slides’ images Image analysis (AI) The details in relation to Proscia technology can be found on this page, Proscia Platform. Proscia Technology – Telepathology One of the key aspects of the Proscia platform is data gathering (slides’ images) from different diagnostic sources. In order to achieve this, Proscia platform supports following: Supports different slide scanning hardware devices to scan the slides and create related …
Niramai uses AI / Thermal Imaging for Breast Cancer Screening
Niramai Health Analytix, a Bengaluru-based startup is creating an AI-powered software system for breast cancer screening. Niramai is using following technologies to achieve the objective of breast cancer screening: Thermal image processing using thermal sensing device (thermal camera) Machine learning algorithm Hardware devices integrated with real-time cloud-based diagnostics; These hardware devices are capable of capturing thermal images What/How of Thermal Image Processing? Thermal image processing, also termed as thermal imaging, is a method of improving visibility of objects in a dark environment by detecting the objects’ infrared radiation and creating an image based on that information. source: techtarget. The key to capturing thermal images of an object is a heat sensor (also called as thermal camera) which is …
AIndra uses AI to Solve Cervical Carcinoma Cancer
AIndra, a Bengaluru-based startup is into the business of building innovative products and technologies to aid computational pathology. Established in 2014, AIndra’s vision is to build state of the art medical devices for screening Cervical Carcinoma. This article is created solely based on my analysis of information found on AIndra’s website. The objective is to make readers aware of some of the following technologies AIndra is using and, how they can be used to solve healthcare problems, in general. The goal is provide food for thought to the readers such that they can use some of these technologies in their future startups. Computation Pathology Telepathology If you work in AIndra, please feel …
15+ AI Startups for Cancer Prediction / Treatment
This is a list of 15+ startups using artificial intelligence (AI) technologies for cancer/oncology prediction / treatment. Please feel free to suggest if any piece of information given below is incorrect or incomplete. This page will be updated from time-to-time. Startup Name Field of Interest Startup Brief OuroTech Cancer treatment Help doctors identify in advance which drugs are most likely to have the biggest impact killing a type of cancer. Doctor Hazel Skin Cancer Helps predict whether you are having from Skin cancer Color Genomics Genetic testing Focus on testing for mutations leading to a higher risk of certain cancers. Mendel.ai Clinical trials AI to match cancer patients with the latest clinical trials Grail Cancer …
Martin Ford on Impact of AI & Robots on Society
This is a featured post on (Martin Ford), a futurist and author focusing on the impact of artificial intelligence (AI) and robotics on society and the economy. What Martin Ford has been saying / talking about? Here are some news feeds on Martin Ford which features his thoughts on AI and related topics: Who’s enjoying fruits of Innovation: In this article, he pointed out that AI is benefitting business owners, managers and investors more than the average workers. Earlier, workers knowing how to operate machines used to make them valuable enough to help them earn their livelihood. In the current age, machines are becoming autonomous and moving ahead in the …
Data Science – How to Scale or Normalize Numeric Data using R
This article represents concepts around the need to normalize or scale the numeric data and code samples in R programming language which could be used to normalize or scale the data. Please feel free to comment/suggest if I missed mentioning one or more important points. Also, sorry for the typos. Following are the two different ways which could be used to normalize the data, and thus, described later in this article: Why Normalize or Scale the data? Min-Max Normalization Z-Score Standardization Why Normalize or Scale the data? There can be instances found in data frame where values for one feature could range between 1-100 and values for other feature could …
I found it very helpful. However the differences are not too understandable for me